huggingface / diffusers

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.
https://huggingface.co/docs/diffusers
Apache License 2.0
25.64k stars 5.3k forks source link

AttributeError: 'NoneType' object has no attribute 'get' #9430

Open molo32 opened 1 month ago

molo32 commented 1 month ago

Name: diffusers Version: 0.30.2

Name: transformers Version: 4.44.2

Loading pipeline components...:  20%  1/5 [00:00<00:00,  9.69it/s] /usr/local/lib/python3.10/dist-packages/transformers/tokenization_utils_base.py:1601: FutureWarning: clean_up_tokenization_spaces was not set. It will be set to True by default. This behavior will be depracted in transformers v4.45, and will be then set to False by default. For more details check this issue: https://github.com/huggingface/transformers/issues/31884 warnings.warn(

AttributeError Traceback (most recent call last) in <cell line: 10>() 8 steps_offset=1, 9 ) ---> 10 pipe = StableDiffusionInpaintPipeline.from_pretrained( 11 "benjamin-paine/stable-diffusion-v1-5-inpainting", 12 torch_dtype=torch.float16,

3 frames /usr/local/lib/python3.10/dist-packages/transformers/modeling_utils.py in from_pretrained(cls, pretrained_model_name_or_path, config, cache_dir, ignore_mismatched_sizes, force_download, local_files_only, token, revision, use_safetensors, *model_args, **kwargs) 3736 metadata = f.metadata() 3737 -> 3738 if metadata.get("format") == "pt": 3739 pass 3740 elif metadata.get("format") == "tf":

AttributeError: 'NoneType' object has no attribute 'get'

SahilCarterr commented 1 week ago

@molo32 Provide the pipeline call code also and Could you also provide your environment information? You can this by running diffusers-cli env